© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10393
    Prev
    Next
    INDEX
    Explanations

    rage and anger expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸įä¸Ĭ
    -0.19
    licity
    -0.18
    aphore
    -0.17
    躺çĿĢ
    -0.17
    æį©
    -0.17
    å£ħ
    -0.16
    Ñģ
    -0.16
    pla
    -0.16
    ities
    -0.16
    ç±Ģ
    -0.16
    POSITIVE LOGITS
    fully
    0.32
    ful
    0.28
    FUL
    0.23
    ingly
    0.23
    ging
    0.20
    ant
    0.20
    ably
    0.19
    0.19
     mẽ
    0.18
    iveness
    0.18
    Activations Density 0.006%

    No Known Activations